From Words to Worlds: Transforming One-line Prompt into Immersive Multi-modal Digital Stories with Communicative LLM Agent
This addresses production scalability and flexibility problems for digital storytellers in entertainment, education, and marketing.
The paper tackles the challenge of scalable digital storytelling production by introducing StoryAgent, a framework that uses LLMs and generative tools to automatically create immersive multi-modal stories from simple prompts. The results show the system can produce coherent digital stories without requiring reference videos.
Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automate and refine digital storytelling. Employing a top-down story drafting and bottom-up asset generation approach, StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. This framework enables efficient production of interactive and consistent narratives across multiple modalities, democratizing content creation and enhancing engagement. Our results demonstrate the framework's capability to produce coherent digital stories without reference videos, marking a significant advancement in automated digital storytelling.